© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205121
    Prev
    Next
    INDEX
    Explanations

    drive traffic, website content

    np_acts-logits-general · gemini-2.5-flash-lite

    steps for tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     mảnh
    0.50
     xray
    0.45
    ⒏
    0.44
     fonctionnent
    0.43
     dhatu
    0.43
    ン
    0.42
    ভি
    0.42
    igraphic
    0.42
    ッキング
    0.42
     expériment
    0.42
    POSITIVE LOGITS
    approche
    0.48
    save
    0.48
    idon
    0.48
    everyone
    0.48
    encour
    0.47
    aver
    0.47
    i
    0.47
    sticks
    0.47
    away
    0.46
    child
    0.46
    Activations Density 0.000%

    No Known Activations